FoundationVIO: Enforcing Metric Scale in Feed-forward Visual-Inertial Odometry
FoundationVIO: Enforcing Metric Scale in Feed-forward Visual-Inertial Odometry
FoundationVIO integrates inertial sensing with geometric foundation models to recover metric scale in visual-inertial odometry. It addresses the scale ambiguity in GFM predictions using a factor-graph approach, achieving competitive odometry estimates and more accurate dense reconstructions compared to existing GFM-enabled SLAM methods. The method runs at approximately real-time on a consumer-grade laptop GPU.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- code: Available Artifact link Open source S5
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
evaluate our method on three datasets with well known sensor systems and demonstrate its compatibility on ubiquitous camera and IMU sensors. The method runs at approximately real-time on a consumer-grade laptop GPU. Code: https://github.com/ori-drs/FoundationVIO.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org